Rotation Equivariant CNNs for Digital Pathology
This work addresses the challenge of histopathology diagnosis for medical applications, providing a novel dataset and benchmark for fundamental machine learning research.
The paper tackles the problem of tumor detection in digital pathology by proposing a rotation equivariant CNN that leverages inherent symmetries in histopathology images, resulting in significantly improved tumor detection performance on a lymph node metastases dataset.
We propose a new model for digital pathology segmentation, based on the observation that histopathology images are inherently symmetric under rotation and reflection. Utilizing recent findings on rotation equivariant CNNs, the proposed model leverages these symmetries in a principled manner. We present a visual analysis showing improved stability on predictions, and demonstrate that exploiting rotation equivariance significantly improves tumor detection performance on a challenging lymph node metastases dataset. We further present a novel derived dataset to enable principled comparison of machine learning models, in combination with an initial benchmark. Through this dataset, the task of histopathology diagnosis becomes accessible as a challenging benchmark for fundamental machine learning research.